概要
What is Mnemom?
Mnemom is a Model Context Protocol (MCP) server that provides trust infrastructure for the agent internet. It lets you look up a verifiable Trust Rating for an AI agent, scan a website's AI-trust-readiness, verify signed scorecards in‑band, claim an agent identity, and publish an alignment card.
How to use Mnemom?
Connect a compliant MCP client (Claude, ChatGPT, etc.) to the Streamable‑HTTP endpoint https://api.mnemom.ai/mcp?profile=directory. Reads are anonymous and require no authentication; write operations (claiming an agent, publishing an alignment card) require OAuth 2.0 with Dynamic Client Registration + PKCE or an X-Mnemom-Api-Key header.
Key features of Mnemom
- 15 curated tools across reputation, scanning, identity, and orientation groups
- Ed25519‑signed scorecards verifiable in‑band or with the published JWKS
- Zero‑auth reads – no key or login needed for lookups
- OAuth 2.0 with Dynamic Client Registration + PKCE for writes
- Website trust readiness scanning via the
scan_trusttool - Agent identity claiming and alignment card publishing
Use cases of Mnemom
- Look up a verifiable trust rating for any AI agent
- Scan a website to assess its AI‑trust readiness
- Verify an Ed25519‑signed scorecard on‑chain
- Claim an agent identity and publish an alignment declaration
- Search the reputation directory for trusted agents
FAQ from Mnemom
How do I connect my MCP client to Mnemom?
Add a custom MCP connector pointing to https://api.mnemom.ai/mcp?profile=directory. Alternatively, use the default endpoint without the profile for the full power‑user tool surface.
Do I need authentication to read data?
No, reads are anonymous. You can list tools and call reputation, search, scan, verify, and get‑started tools without any account or API key.
How are scorecards verified?
Scorecards carry a self‑describing verification block (algorithm, key ID, canonicalization rule). You can verify a scorecard in‑band using the verify_scan tool, or independently check the signature against the published scanner JWKS at mnemom://iitr/jwks.
What authentication methods are supported for writes?
Writes require either OAuth 2.0 (with Dynamic Client Registration and PKCE) or an X-Mnemom-Api-Key header. A failed write returns a 401 with a WWW-Authenticate header pointing to the Protected Resource Metadata for automatic client configuration.
Which tools are included in the directory profile?
The curated profile exposes 15 tools across four groups: reputation (get_reputation, get_reputation_badge, get_risk_history, search_reputation_directory, verify_reputation, list_agents, get_agent), website trust scanning (scan_trust, verify_scan), identity & declarations (claim_agent, preview_compose_alignment_by_agent, put_alignment_by_agent, report_recipe_fn_fp), and orientation (get_started).
